Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 33
Sivu 32
We shall show that if the positions of the N pattern points satisfy some quite mild
conditions , the number of dichotomies that can be implemented by a function will
depend only on the number of patterns N and the number of parameters M + 1 ...
We shall show that if the positions of the N pattern points satisfy some quite mild
conditions , the number of dichotomies that can be implemented by a function will
depend only on the number of patterns N and the number of parameters M + 1 ...
Sivu 33
Thus , depending only on the condition of general position of the points , and
otherwise independent of the configuration of the points , we observe from Fig . 2
: 9a that L ( 4 , 2 ) = 2 . 7 = 14 . This number is to be compared with the 24 = 16
total ...
Thus , depending only on the condition of general position of the points , and
otherwise independent of the configuration of the points , we observe from Fig . 2
: 9a that L ( 4 , 2 ) = 2 . 7 = 14 . This number is to be compared with the 24 = 16
total ...
Sivu 36
Suppose that we have a set X of N points and a set Z of K points ( K < d ) in Ed .
We desire to know the number Lz ( N , d ) of linear dichotomies of X achievable
by a hyperplane constrained to contain all the points of z . We shall assume that ...
Suppose that we have a set X of N points and a set Z of K points ( K < d ) in Ed .
We desire to know the number Lz ( N , d ) of linear dichotomies of X achievable
by a hyperplane constrained to contain all the points of z . We shall assume that ...
Mitä ihmiset sanovat - Kirjoita arvostelu
Yhtään arvostelua ei löytynyt.
Muita painoksia - Näytä kaikki
Yleiset termit ja lausekkeet
adjusted apply assume bank belonging to category called changes Chapter cluster committee components consider consists contains correction corresponding covariance decision surfaces define denote density depends derivation Development discriminant functions discussed distance distribution element equal error-correction estimates example exists expression FIGURE fixed gi(X given implemented important initial layered machine linear dichotomies linear machine linearly separable matrix measurements networks normal Note optimum origin parameters partition pattern classifier pattern hyperplane pattern space pattern vector piecewise linear plane points positive presented probability problem proof properties proved PWL machine quadric reduced regions respect response rule sample mean selection separable shown side solution space specific Stanford step Suppose theorem theory threshold training methods training procedure training sequence training subsets transformation values weight vectors zero
Viitteet tähän teokseen
A Probabilistic Theory of Pattern Recognition Luc Devroye,László Györfi,Gabor Lugosi Rajoitettu esikatselu - 1997 |